First Demonstration of Multi-Agent LLM System for Million-Scale Optical Link Management in Global Production AIDCs
2026-08-24 • Multiagent Systems
Multiagent Systems
AI summaryⓘ
The authors created a system that uses large language models (LLMs) working together to automatically find and fix problems in millions of optical network links. They improved the system using special training techniques and by remembering past issues to get better over time. When tested over ten weeks, their system caught almost 98% of faults and reduced incidents by over 60%, doing better than other existing LLM-based methods. This shows their approach is effective for managing network faults at a large scale.
large language modelsmulti-agent systemfault managementoptical networkssupervised fine-tuningmemory evolutionfield data evaluationF1 scorefault incident reduction
Authors
Jingyi Su, Yihao Zhang, Dianxuan Fu, Leiyan Fei, Juan Wang, Mengfan Dai, Qing Liu, Xiong Wu, Yufeng Jiang, Cheng Chen, Bowen Zhang, Peilong Wang, Xi Chen, Zonglong He, Hongchen Yu, Zhicheng Ye, Weisheng Hu, Qunbi Zhuge
Abstract
We present the first LLM-powered multi-agent system for autonomous fault management across millions of optical links in production AIDCs. Refined via SFT and continuous memory evolution, it achieves 97.7% F1 and over 60% fault-incident reduction, outperforming SOTA LLMs on a ten-week field data evaluation.